jpmschweitzerandClaude Opus 4.6 be6f2a3db9 feat(voice): add hardware detection + dynamic sr-voice instance management (Phase 4) ...

GPU-aware scaling: NVIDIA (nvidia-smi), AMD (sysfs VRAM), Apple Silicon
(unified memory). GPU mode detected at install, persisted to settings.
Scaling ceiling: (free_resource - existing_llm_usage) / 2 / per_instance_cost.
VoiceInstanceManager spawns/stops sr-voice processes on unique ports.
Battery detection scales to 1 worker.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-07 17:32:20 +01:00

..

data/templates

fix(simulation): address PR #75 review — vision components, triangle validation, FNV-1a, KG gating

2026-02-27 19:02:43 +01:00

sr-voice

feat(engine): add sr-voice LLM inference service for NPC voice pipeline

2026-03-07 15:44:37 +01:00

src

feat(voice): add hardware detection + dynamic sr-voice instance management (Phase 4)

2026-03-07 17:32:20 +01:00

tests

fix(simulation): address PR #85 review — warnings and polish items

2026-03-05 10:59:38 +01:00

.clippy.toml

feat(ci): ban HashMap in simulation crate via clippy (#343)

2026-02-19 13:34:04 +01:00

Cargo.lock

feat(voice): add cache, queue, and worker modules (D-138, Spike 2 Phase 2)

2026-03-07 17:09:24 +01:00

Cargo.toml

feat(voice): add cache, queue, and worker modules (D-138, Spike 2 Phase 2)

2026-03-07 17:09:24 +01:00